11mlabs/indri-0.1-124m-tts

Full fine-tune vs openai-community/gpt2. Fine-tune: 100% of the weights changed, across 12 of 12 layers.

Tensors changed: Norms 50/50, Attention 48/48, MLP 48/48, Embeddings 1/1

1 derivatives checked

• mradermacher/indri-0.1-124m-tts-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse